Scholarlink

<p>Modern space exploration requires superior Propelling systems and dual bell nozzles present a promising solution for enhancing rocket propulsion system performance across varied flight regimes. This study offers a comprehensive optimization and analysis of dual bell nozzle design for advanced rockets. By employing Machine Learning with an Artificial Neural Network model, we developed a novel approach to rapidly optimize dual bell nozzle geometry for a specified exit Mach number, addressing the complex calculations typically associated with nozzle design. The algorithm generated a nozzle configuration capable of efficient operation in both low and high-altitude conditions. To validate results, we conducted detailed computational simulations using ANSYS Fluent. The analysis corroborated the model predictions, revealing key performance characteristics including a maximum exhaust velocity of approximately 2200&#xa0;m/s and an exit Mach number of 5.8, aligning closely with the optimization. Our study contributes to the advancement of space propulsion technology by demonstrating the potential of AI-driven optimization in nozzle design.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Design optimization and computational validation of dual bell nozzle using ANN algorithm

  • 期刊论文

  • 发表日期：

    2025年6月2日

查看全文
  • Taranjit Singh,
  • Balaji Ravi

摘要

Modern space exploration requires superior Propelling systems and dual bell nozzles present a promising solution for enhancing rocket propulsion system performance across varied flight regimes. This study offers a comprehensive optimization and analysis of dual bell nozzle design for advanced rockets. By employing Machine Learning with an Artificial Neural Network model, we developed a novel approach to rapidly optimize dual bell nozzle geometry for a specified exit Mach number, addressing the complex calculations typically associated with nozzle design. The algorithm generated a nozzle configuration capable of efficient operation in both low and high-altitude conditions. To validate results, we conducted detailed computational simulations using ANSYS Fluent. The analysis corroborated the model predictions, revealing key performance characteristics including a maximum exhaust velocity of approximately 2200 m/s and an exit Mach number of 5.8, aligning closely with the optimization. Our study contributes to the advancement of space propulsion technology by demonstrating the potential of AI-driven optimization in nozzle design.